LangChain

This section details KDB.AI and the integration with LangChain.

KDB.AI can integrate with LangChain, which utilizes LLMs to offer a more human-like interaction.

LangChain is a framework designed to simplify the creation of applications using large language models. As a language model integration framework, LangChain's use-cases largely overlap with those of language models in general, including document analysis and summarization, chatbots, and code analysis. - Wikipedia

Check out the official LangChain repository on GitHub.

Getting Started

Prerequisites

Python 3
Pip
Git

Install

Bash

Copy

#run
pip install langchain
git clone -b KDBAI_v1.4 https://github.com/KxSystems/langchain.git
cd langchain/libs/community
pip install .

#or
pip install ipython jupyter pyarrow openai pypdf tiktoken kdbai-client langchain

Start Jupyter

Bash

Copy

jupyter notebook

If you need help with the integration, feel free to reach out to the KDB.AI Slack community or email support@kdb.ai.

Examples

Check out Building applications with LLMs through composability for KDB.AI 1.4.0. Run a Notebook example to use KDB.AI as a LangChain vector store. You need a KDB.AI endpoint and API keys for KDB.AI and OpenAI.
Open the RAG sample and the RAG evaluation sample in our GitHub repo.
Run the RAG and RAG evaluation notebooks directly in Google Colab.
Watch this YouTube tutorial demonstrating Retrieval Augmented Generation with LangChain and Vector Databases.